Qwen3-VL-235B-A22B-Instruct
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
Params
235.7 B
Context
—
Downloads 30d
916 K
Likes
415
Download history
daily snapshots · 89 days
▲ 0 in the last 30 days (0.0%)
916 K916 K
Sep 25Oct 5Oct 15Oct 24
1.8 M916 K
Jul 28Aug 26Sep 25Oct 24
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 471.3 GB | 554.3 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.21
input / 1M
$1.90
output / 1M
$0.10
cached input / 1M
$2.11
1M in + 1M out
- Context window
- 131,072 tokens
- Max output
- 32,768 tokens
- Providers
- 3
- Cheapest provider
- DeepInfra · $0.20 / $0.88
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 9.9 / — / —
✓ Tool calling
✗ Reasoning
✓ Structured outputs
✓ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- Qwen3VLMoeForConditionalGeneration
- Parameters
- 235.7 B
- Tensor type
- BF16
- Licence
- apache-2.0
- First seen on the Hub
- 2025-09-22
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any image-text-to-text model
Popular comparisons